© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 17610
    Prev
    Next
    INDEX
    Explanations

    specific punctuation and formatting cues in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hoo
    -0.07
    hiro
    -0.06
    nad
    -0.06
    òi
    -0.06
    çIJ
    -0.06
    ısından
    -0.06
    memberof
    -0.06
    CRC
    -0.06
    uzz
    -0.06
    ngth
    -0.06
    POSITIVE LOGITS
    iles
    0.07
     _{}
    0.07
    isci
    0.07
    SCII
    0.06
    arch
    0.06
    fax
    0.06
    ILES
    0.06
    <Unit
    0.06
    olon
    0.06
     Fel
    0.06
    Activations Density 0.009%

    No Known Activations